Instructions to use fjmgAI/b1-R1-Zero-3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fjmgAI/b1-R1-Zero-3B-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("fjmgAI/b1-R1-Zero-3B-GGUF", dtype="auto")

llama-cpp-python

How to use fjmgAI/b1-R1-Zero-3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="fjmgAI/b1-R1-Zero-3B-GGUF",
	filename="unsloth.BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use fjmgAI/b1-R1-Zero-3B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf fjmgAI/b1-R1-Zero-3B-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf fjmgAI/b1-R1-Zero-3B-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf fjmgAI/b1-R1-Zero-3B-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf fjmgAI/b1-R1-Zero-3B-GGUF:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf fjmgAI/b1-R1-Zero-3B-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf fjmgAI/b1-R1-Zero-3B-GGUF:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf fjmgAI/b1-R1-Zero-3B-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fjmgAI/b1-R1-Zero-3B-GGUF:BF16

Use Docker

docker model run hf.co/fjmgAI/b1-R1-Zero-3B-GGUF:BF16

LM Studio
Jan
Ollama
How to use fjmgAI/b1-R1-Zero-3B-GGUF with Ollama:
```
ollama run hf.co/fjmgAI/b1-R1-Zero-3B-GGUF:BF16
```

Unsloth Studio

How to use fjmgAI/b1-R1-Zero-3B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for fjmgAI/b1-R1-Zero-3B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for fjmgAI/b1-R1-Zero-3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fjmgAI/b1-R1-Zero-3B-GGUF to start chatting

How to use fjmgAI/b1-R1-Zero-3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fjmgAI/b1-R1-Zero-3B-GGUF:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "fjmgAI/b1-R1-Zero-3B-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use fjmgAI/b1-R1-Zero-3B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fjmgAI/b1-R1-Zero-3B-GGUF:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default fjmgAI/b1-R1-Zero-3B-GGUF:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use fjmgAI/b1-R1-Zero-3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf fjmgAI/b1-R1-Zero-3B-GGUF:BF16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "fjmgAI/b1-R1-Zero-3B-GGUF:BF16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use fjmgAI/b1-R1-Zero-3B-GGUF with Docker Model Runner:
```
docker model run hf.co/fjmgAI/b1-R1-Zero-3B-GGUF:BF16
```

Lemonade

How to use fjmgAI/b1-R1-Zero-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fjmgAI/b1-R1-Zero-3B-GGUF:BF16

Run and chat with the model

lemonade run user.b1-R1-Zero-3B-GGUF-BF16

List all available models

lemonade list

Fine-Tuned Model

fjmgAI/b1-R1-Zero-3B-GGUF

Base Model

unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit

Fine-Tuning Method

Fine-tuning was performed using unsloth, an efficient fine-tuning framework optimized for low-resource environments and Huggingface's TRL library.

Dataset

Kukedlc/dpo-orpo-spanish-15k

Description

A Spanish-language dataset containing 15,000 examples, designed for Direct Preference Optimization (DPO) or Outcome-Regularized Preference Optimization (ORPO).

Adaptation

The dataset was adapted to a reasoning-based format for GPRO, enhancing its ability to guide preference-based decision-making during fine-tuning. This adaptation ensures better alignment with instruction-following tasks in Spanish.

Fine-Tuning Details

The model was trained using the GPRO algorithm, leveraging structured preference data to refine its response generation.
The model was fine-tuned to maintain its 4-bit quantization (bnb-4bit) for memory efficiency while aligning its outputs with the characteristics of the Spanish dataset.
The focus was on retaining the model's instructional abilities while improving its understanding and generation of Spanish text.

Purpose

This fine-tuned model is intended for Spanish-language applications that require efficient AI that follows instructions using a lightweight reasoning process.